BIGKnight / Deformable_conv2d_pytorch
deformable_conv2d layer implemented in pytorch
Stars: ✭ 53
Labels
Projects that are alternatives of or similar to Deformable conv2d pytorch
Qualia2.0
Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.
Stars: ✭ 41 (-22.64%)
Mutual labels: cuda
Hornet
Hornet data structure for sparse dynamic graphs and matrices
Stars: ✭ 49 (-7.55%)
Mutual labels: cuda
Smallpt Parallel Bvh Gpu
A GPU implementation of smallpt (http://www.kevinbeason.com/smallpt/) with Bounding Volume Hierarchy (BVH) tree.
Stars: ✭ 36 (-32.08%)
Mutual labels: cuda
Octree Slam
Large octree map construction and rendering with CUDA and OpenGL
Stars: ✭ 40 (-24.53%)
Mutual labels: cuda
Carlsim3
CARLsim is an efficient, easy-to-use, GPU-accelerated software framework for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.
Stars: ✭ 52 (-1.89%)
Mutual labels: cuda
Singularity Tutorial
Tutorial for using Singularity containers
Stars: ✭ 46 (-13.21%)
Mutual labels: cuda
Soul Engine
Physically based renderer and simulation engine for real-time applications.
Stars: ✭ 37 (-30.19%)
Mutual labels: cuda
Nvidia libs test
Tests and benchmarks for cudnn (and in the future, other nvidia libraries)
Stars: ✭ 36 (-32.08%)
Mutual labels: cuda
Object Detection And Location Realsensed435
Use the Intel D435 real-sensing camera to realize target detection based on the Yolov3 framework under the Opencv DNN framework, and realize the 3D positioning of the Objection according to the depth information. Real-time display of the coordinates in the camera coordinate system.ADD--Using Yolov5 By TensorRT model,AGX-Xavier,RealTime Object Detection
Stars: ✭ 36 (-32.08%)
Mutual labels: cuda
Cuda Convnet2.torch
Torch7 bindings for cuda-convnet2 kernels!
Stars: ✭ 42 (-20.75%)
Mutual labels: cuda
Pamtri
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification (ICCV 2019) - Official PyTorch Implementation
Stars: ✭ 53 (+0%)
Mutual labels: cuda
Hungariangpu
An GPU/CUDA implementation of the Hungarian algorithm
Stars: ✭ 51 (-3.77%)
Mutual labels: cuda
Deformable_Conv2d_Pytorch
deformable_conv2d layer implemented in pytorch. and I wrote several articles on ZHIHU, you can read it for more detailed information
1.deformable变形卷积pytorch实现(第一节Custom op extension) 2.deformable变形卷积pytorch实现(第二节deformable_conv2d 实现一)
besides, I also complete an example net, here
and I'm very sorry that I did not implement the swapaxis methods, so the im2col_step parameter are only allowed using value one.
ENVIRONMENT CONFIGURATION
- OS: ubuntu16.04
- GPU: 1 gtx1080Ti
- LANGUAGE: python3.6.8 & c++11 & cuda c
- DL FRAMEWORK: Pytorch 1.0.1
- ANCILLARY LIB: setuptools: 36.4.0, numpy: 1.15.4
- GPU API: NVIDIA CUDA 9.0 & cuDNN 7.0
- COMPILE: nvcc & gcc 5.4.0
INSTALL PROCEDURE
- cd "current project"
- run mask.sh
tips: you need to modify the path parameters first. and all the -I and -L path in the nvcc and g++ orders need to be checked, make sure they are the correct path in your system
- import deformable_conv2d_wrapper.py into your python file, and you can call the class BasicDeformableConv2D then.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].